browser-use
AI-powered browser automation using the browser-use library (v0.11+). Drives a real Chromium browser with an LLM agent to navigate, fill forms, click, scrape, and extract structured data from any website. Use when: (1) automating web tasks end-to-end (login, form submission, multi-step flows), (2) scraping dynamic JS-rendered pages, (3) registering for internet services as Alex Chen, (4) solving CAPTCHAs and bypassing browser-checks, (5) extracting structured data from web UIs, (6) any task that requires interacting with a real browser. NOT for: static HTML fetching (use web_fetch), simple API calls, or Cloudflare-protected APIs with a valid token.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/bowen31337/alex-browser-useWhat This Skill Does
The browser-use skill is a high-performance, AI-driven automation agent designed to navigate the web just like a human. By leveraging the browser-use library (v0.11+), it controls a full-featured Chromium browser, enabling complex multi-step interactions such as authenticating via OAuth, completing dynamic forms, and scraping data from JavaScript-heavy web applications. It serves as your primary tool for end-to-end web interaction where simple HTTP requests fail or require complex browser-based security checks.
Installation
You can integrate this skill into your OpenClaw environment using the following command:
clawhub install openclaw/skills/skills/bowen31337/alex-browser-use
Ensure your system is configured with uv for dependency management. Scripts must always be executed using uv run python script.py to maintain the correct environment and security context.
Use Cases
This skill is ideal for tasks requiring stateful sessions and visual context. Common use cases include:
- Automating sign-ups and registrations for web services.
- Scraping data from dashboards that require login or interactive filtering.
- Managing social media interactions or posting content where UI-based validation is required.
- Completing multi-page checkout or verification processes.
- Extracting structured information from sites protected by standard bot-detection mechanisms.
Example Prompts
- "Go to the dashboard at example.com, login using the saved credentials, navigate to the reports tab, and export the Q1 data as a CSV."
- "Search for the latest public filings for Acme Corp on the SEC EDGAR site and summarize the key risks mentioned in the recent 10-Q."
- "Open the registration portal for the upcoming tech conference, fill out the form using my profile details, and let me know when you reach the payment confirmation page."
Tips & Limitations
To ensure success, you must adhere to the mandatory anti-detection rules. Always use stealth_session() to hide automation flags and spoof browser fingerprints. Avoid using standard fill methods; instead, emulate human typing with variable delays between keystrokes to bypass bot-detection algorithms. Never fetch pages via static HTTP if they require dynamic interaction, and prioritize direct navigation to action URLs to reduce the risk of detection. Note that this skill is not suitable for simple API calls or static data fetching; for those cases, use the native web_fetch skill to save resources.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-bowen31337-alex-browser-use": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: network-access, code-execution, external-api
Related Skills
Terse
Skill by bowen31337
Identity Resolver
Skill by bowen31337
agent-self-governance
Self-governance protocol for autonomous agents: WAL (Write-Ahead Log), VBR (Verify Before Reporting), ADL (Anti-Divergence Limit), VFM (Value-For-Money), and IKL (Infrastructure Knowledge Logging). Use when: (1) receiving a user correction — log it before responding, (2) making an important decision or analysis — log it before continuing, (3) pre-compaction memory flush — flush the working buffer to WAL, (4) session start — replay unapplied WAL entries to restore lost context, (5) any time you want to ensure something survives compaction, (6) before claiming a task is done — verify it, (7) periodic self-check — am I drifting from my persona? (8) cost tracking — was that expensive operation worth it? (9) discovering infrastructure — log hardware/service specs immediately.
rsi-loop
Recursive Self-Improvement (RSI) loop for EvoClaw agents. Provides a structured observe→analyze→synthesize→deploy pipeline that enables agents to detect their own failure patterns and generate concrete improvement proposals (new skills, routing fixes, SOUL.md updates, memory improvements). Use when: (1) logging a task outcome (success/fail/quality), (2) running periodic self-improvement analysis, (3) reviewing or deploying improvement proposals, (4) integrating RSI into EvoClaw hub/edge agents via MQTT, (5) checking agent health score, (6) any mention of "self-improvement", "recursive improvement", "fix my own mistakes", "improvement loop", or "agent evolution". Core EvoClaw primitive.
clawchain
ClawChain RPC client for EvoClaw agents. Connects to Substrate-based blockchain, queries on-chain agent data, submits transactions, and enables agents to participate in on-chain governance and reputation tracking. Use when working with ClawChain L1 blockchain, agent DIDs, token economics, or agent reputation systems.